AUTHOR=Frolov Alexander , Bobrov Pavel , Biryukova Elena , Isaev Mikhail , Kerechanin Yaroslav , Bobrov Dmitry , Lekin Alexander 

TITLE=Using Multiple Decomposition Methods and Cluster Analysis to Find and Categorize Typical Patterns of EEG Activity in Motor Imagery Brain–Computer Interface Experiments

JOURNAL=Frontiers in Robotics and AI

VOLUME=Volume 7 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/robotics-and-ai/articles/10.3389/frobt.2020.00088

DOI=10.3389/frobt.2020.00088

ISSN=2296-9144

ABSTRACT=In the paper the sources of EEG activity in motor imagery BCI control experiments were investigated. Sixteen linear decomposition methods for EEG source separation were compared according to different criteria. The criteria were mutual information reduction between the source activities and physiological plausibility. The latter was tested by estimating dipolarity of the source topographic maps, i.e. accuracy of approximating the map by potential distribution from a single current dipole, as well as by specificity of the source activity for different motor imagery tasks. The decomposition methods were also compared by number of shared components found. The results indicate that most of the dipolar components are found by the Independent Component Analysis Methods AMICA and PWCICA which also provide the highest information reduction. These two methods also found the most task-specific EEG patterns among the blind source separation algorithms used. They are outperformed only by non-blind Common Spatial Pattern methods in terms of the pattern specificity. The components found by all the methods were clustered using the attractor neural network with increasing activity. The results of the cluster analysis revealed the most frequent patterns of electrical activity occurring in the experiments. The patterns reflect blinking, eye movements, sensorimotor rhythm suppression during the motor imagery, activations in precuneus, supplementary motor area, and premotor areas of both hemispheres. Overall, the multi-method decomposition with subsequent clustering and task-specificity estimation is a viable and informative procedure of processing the recordings of electrophysiological experiments.